A domain-independent agent architecture for adaptive operation in evolving open worlds

DOI10.1016/J.ARTINT.2024.104161MaRDI QIDQ6592985zbMATH OpenFDO

Authors Shiwali Mohan, Wiktor Piotrowski, Roni Stern, Sachin Grover, Sookyung Kim, Jacob Le, Yoni Sher, Johan de Kleer

Publication date 26 August 2024

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.ARTINT.2024.104161

zbMATH Keywords

agent architecturesagentsintegrated intelligent systemsmodel-based reasoningnovelty reasoningopen-world learningPDDL+planning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Logic in artificial intelligence (68T27) Agent technology and artificial intelligence (68T42)

Recommendations

• scientific article; zbMATH DE number 1728568
• scientific article; zbMATH DE number 1560502
• Novelty detection improves performance of reinforcement learners in fluctuating, partially observable environments
• Extending adaptive world modeling by identifying and handling insufficient knowledge models
• Agents in proactive environments

Cites work

• A Comprehensive Framework for Learning Declarative Action Models
• COLIN: planning with continuous linear numeric change
• Diagnosing multiple faults
• scientific article; zbMATH DE number 4154239 (Why is no real title available?)
• scientific article; zbMATH DE number 2038893 (Why is no real title available?)
• Interval-based relaxation for general numeric planning
• Learning action models from plan examples using weighted MAX-SAT
• Learning action models with minimal observability
• Modelling mixed discrete-continuous domains for planning
• Reinforcement learning. An introduction
• Updating action domain descriptions

This page was built for publication: A domain-independent agent architecture for adaptive operation in evolving open worlds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6592985)